Expert Systems with Applications: An International Journal
| Hi-index | 0.00 |
The neural network approach is applied to the prediction of the flow of the River Nile. A multilayer feed-forward network is constructed and trained by the back propagation algorithm. We propose several different methods for single-step ahead forecast and multi-step ahead forecast in an attempt to get the least prediction error. These methods investigate different ways to preprocess the inputs and the outputs. We consider ten-days ahead forecast and one-month ahead forecast. In both cases good results were observed.